基于改进U-Net网络的相位解包裹技术研究  

Research on phase unwrapping technology based on improved U-Net network

作　　者：徐瑞书 罗笑南 沈瑶琼[1,2] 郭创为 张文涛 管钰晴 傅云霞 雷李华[1,2] Xu Ruishu;Luo Xiaonan;Shen Yaoqiong;Guo Chuangwei;Zhang Wentao;Guan Yuqing;Fu Yunxia;Lei Lihua(Shanghai Institute of Measurement and Testing Technology,Shanghai 201203,China;Shanghai Key Laboratory of Online Testing and Control Technology,Shanghai 201203,China;School of Computer Science and Information Security,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]上海市计量测试技术研究院,上海201203 [2]上海在线检测与控制技术重点实验室,上海201203 [3]桂林电子科技大学计算机与信息安全学院,广西桂林541004

出　　处：《红外与激光工程》2024年第2期120-133,共14页Infrared and Laser Engineering

基　　金：国家重点研发计划项目(2021YFF0603300);上海市市场监督管理局项目(D00RJ2310);上海市在线检测与控制技术重点实验室基金项目(A04202223003)。

摘　　要：提出了一种结合深度学习的空间相位解包裹方法,采用基于改进U-Net网络的编码器-解码器架构,同时加入包含双向长短期记忆网络(BILSTM)的CBiLSTM模块,并且结合注意力机制,避免了典型卷积神经网络学习全局空间依赖关系的固有缺陷的同时增强了深度学习模型对相位解包裹任务中的关键信息的关注能力。通过大量的模拟数据,验证了文中方法在严重噪声(SNR=0)、不连续条件和混叠条件下的鲁棒性,在以上三种情况下,同其他深度学习网络模型进行对比,文中所提出的网络模型的归一化均方根误差(NRMSE)分别为0.75%、1.81%和1.68%;结构相似性指数(SSIM)分别为0.98、0.92和0.94;峰值信噪比(PSNR)分别为40.87、32.56、37.38;同时计算时间显著减少,适合应用到需要快速准确的空间相位解包裹任务中去。通过实际测量数据,验证了文中提出网络模型的可行性。该研究将双向长短期记忆网络(BILSTM)和注意力机制同时引入光学相位解包裹问题中,为解决复杂相位场的解包裹提供了新的思路和方案。Objective Objective Phase Measurement Deflectometry(PMD)is widely employed in free-form surface transmission wavefront detection due to its simplicity,high accuracy,and broad detection range.Achieving highprecision phase acquisition is a critical step in the measurement and detection process.The phase unwrapping task,crucial in optics,plays a pivotal role in optical interferometry,magnetic resonance imaging,fringe projection profilometry(FPP),and other fields[1-4].The challenge lies in recovering a continuously varying true phase signal from the observed wrapped phase signal within the range of[-π,π].While the ideal phase unrolling involves adding or subtracting 2πat each pixel based on the phase difference between adjacent pixels,practical applications face challenges such as noise and phase discontinuity,leading to poles in the wrapped phase[5].These poles result in accumulated computational errors during the unwrapping process,causing phase unwrapping failures.Various methods are employed to unwrap and obtain the real phase distribution.To address these challenges,this paper proposes a phase unwrapping algorithm based on an improved U-Net network.Methods During the model training process,a composite loss function is defined to train the network based on the specific problem of spatial phase unwrapping.To address these challenges,this paper proposes a phase unwrapping algorithm based on an improved U-Net network.This algorithm utilizes U-Net as the basic network,integrates the CBiLSTM module for modeling time series,introduces an attention mechanism for enhanced generalization,and explores optimized loss functions.The proposed network model is validated through simulated and real datasets,showcasing its outstanding performance under noise,discontinuity,and aliasing conditions.The introduction of the attention mechanism enables better capture of global spatial relationships,while CBiLSTM effectively captures and stores long-term dependencies through memory unit structures.Memory units selectively remember and

关 键 词：相位解包裹 深度学习 注意力机制 长短期记忆网络 卷积神经网络 

分 类 号：TH741[机械工程—光学工程]